xtremedistil-l6-h256-uncased-question-vs-statement-classifier

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

xtremedistil-l6-h256-uncased-question-vs-statement-classifier

This model is a fine-tuned version of microsoft/xtremedistil-l6-h256-uncased on question-vs-statement-classifier dataset, which is a clone of the kaggle Questions vs Statements Classification dataset.

It achieves the following results on the evaluation set:

• Train Loss: 0.0227
• Train Sparse Categorical Accuracy: 0.9894
• Validation Loss: 0.0294
• Validation Sparse Categorical Accuracy: 0.9868
• Epoch: 3

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Framework versions

• Transformers 4.20.1
• TensorFlow 2.9.1
• Datasets 2.3.2
• Tokenizers 0.12.1